Physical-Based Event Camera Simulator

被引:0
作者
Han, Haiqian [1 ]
Lyu, Jiacheng [1 ]
Li, Jianing [1 ]
Wei, Henglu [1 ]
Li, Cheng [2 ]
Wei, Yajing [2 ]
Chen, Shu [2 ]
Ji, Xiangyang [1 ]
机构
[1] Tsinghua Univ, Beijing 100084, Peoples R China
[2] Beijing Xiaomi Mobile Software Co Ltd, Beijing, Peoples R China
来源
COMPUTER VISION - ECCV 2024, PT XLV | 2025年 / 15103卷
基金
中国国家自然科学基金;
关键词
Event camera simulation; Physics-based vision; Hyperspectral data analysis;
D O I
10.1007/978-3-031-72995-9_2
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Existing event camera simulators primarily focus on the process of generating video events and often overlook the entire optical path in real-world camera systems. To address this limitation, we propose a novel Physical-based Event Camera Simulator (PECS), which is able to generate a high-fidelity realistic event stream by directly interfacing with the 3D scene. Our PECS features a lens simulation block for accurate light-to-sensor chip replication and a multispectral rendering module for precise photocurrent generation. We present two spatiotemporal event metrics to assess the similarity between simulated and actual camera events. Experimental results demonstrate that our PECS outperforms four state-of-the-art simulators by a large margin in terms of event-based signal fidelity. We integrate our PECS into the UE platform to generate extensive multi-task synthetic datasets and evaluate its effectiveness in downstream vision tasks (e.g., video reconstruction). Our open-source code is available at https://github.com/lanpokn/PECS_trail_version.
引用
收藏
页码:19 / 35
页数:17
相关论文
共 57 条
[1]   Event-LSTM: An Unsupervised and Asynchronous Learning-Based Representation for Event-Based Data [J].
Annamalai, Lakshmi ;
Ramanathan, Vignesh ;
Thakur, Chetan Singh .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (02) :4678-4685
[2]  
Baek S, 2020, 2020 2ND IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE CIRCUITS AND SYSTEMS (AICAS 2020), P79, DOI [10.1109/AICAS48895.2020.9073963, 10.1109/aicas48895.2020.9073963]
[3]  
Bellekens B., 2015, INT J ADV INTELL SYS, V8, P118
[4]  
Bhattacharya A, 2023, Arxiv, DOI arXiv:2310.02437
[5]  
Bi Y, 2017, IEEE IMAGE PROC, P1990, DOI 10.1109/ICIP.2017.8296630
[6]  
Bocca A., 2019, AEIT AUTOMOTIVE, P1
[7]   Event-Based Vision: A Survey [J].
Gallego, Guillermo ;
Delbruck, Tobi ;
Orchard, Garrick Michael ;
Bartolozzi, Chiara ;
Taba, Brian ;
Censi, Andrea ;
Leutenegger, Stefan ;
Davison, Andrew ;
Conradt, Jorg ;
Daniilidis, Kostas ;
Scaramuzza, Davide .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (01) :154-180
[8]   Video to Events: Recycling Video Datasets for Event Cameras [J].
Gehrig, Daniel ;
Gehrig, Mathias ;
Hidalgo-Carrio, Javier ;
Scaramuzza, Davide .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, :3583-3592
[9]   Approximate k-d tree search for efficient ICP [J].
Greenspan, M ;
Yurick, M .
FOURTH INTERNATIONAL CONFERENCE ON 3-D DIGITAL IMAGING AND MODELING, PROCEEDINGS, 2003, :442-448
[10]   How to Learn a Domain-Adaptive Event Simulator? [J].
Gu, Daxin ;
Li, Jia ;
Zhang, Yu ;
Tian, Yonghong .
PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, :1275-1283